[v1.05] Clean up previous commit

Makefile

@@ -7,8 +7,8 @@ PREFIX ?= /usr
 
 SRC_COMMON=src/common/
 
-COMMON_SRC = $(SRC_COMMON)main.c $(SRC_COMMON)cpu.c $(SRC_COMMON)udev.c $(SRC_COMMON)printer.c $(SRC_COMMON)args.c $(SRC_COMMON)global.c
-COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_COMMON)printer.h $(SRC_COMMON)args.h $(SRC_COMMON)global.h
+COMMON_SRC = $(SRC_COMMON)main.c $(SRC_COMMON)cpu.c $(SRC_COMMON)udev.c $(SRC_COMMON)printer.c $(SRC_COMMON)args.c $(SRC_COMMON)global.c $(SRC_COMMON)freq.c
+COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_COMMON)printer.h $(SRC_COMMON)args.h $(SRC_COMMON)global.h $(SRC_COMMON)freq.h
 
 ifneq ($(OS),Windows_NT)
 	GIT_VERSION := "$(shell git describe --abbrev=4 --dirty --always --tags)"
@@ -32,8 +32,8 @@ ifneq ($(OS),Windows_NT)
 		CFLAGS += -DARCH_PPC -std=gnu99 -fstack-protector-all -Wno-language-extension-token
 	else ifeq ($(arch), $(filter $(arch), arm aarch64_be aarch64 arm64 armv8b armv8l armv7l armv6l))
 		SRC_DIR=src/arm/
-		SOURCE += $(COMMON_SRC) $(SRC_DIR)midr.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_COMMON)pci.c $(SRC_DIR)udev.c
-		HEADERS += $(COMMON_HDR) $(SRC_DIR)midr.h $(SRC_DIR)uarch.h  $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_COMMON)pci.h $(SRC_DIR)udev.c $(SRC_DIR)socs.h
+		SOURCE += $(COMMON_SRC) $(SRC_DIR)midr.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_DIR)udev.c
+		HEADERS += $(COMMON_HDR) $(SRC_DIR)midr.h $(SRC_DIR)uarch.h  $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_DIR)udev.c $(SRC_DIR)socs.h
 		CFLAGS += -DARCH_ARM -Wno-unused-parameter -std=c99 -fstack-protector-all
 
 		os := $(shell uname -s)

src/arm/midr.c

@@ -14,6 +14,7 @@
 
 #include "../common/global.h"
 #include "../common/soc.h"
+#include "../common/freq.h"
 #include "udev.h"
 #include "midr.h"
 #include "uarch.h"
@@ -41,6 +42,12 @@ struct frequency* get_frequency_info(uint32_t core) {
 
   freq->base = UNKNOWN_DATA;
   freq->max = get_max_freq_from_file(core);
+  #ifdef __linux__
+    if (freq->max == UNKNOWN_DATA) {
+      printWarn("Unable to find max frequency from udev, measuring CPU frequency");
+      freq->max = measure_max_frequency(core);
+    }
+  #endif
 
   return freq;
 }

src/arm/soc.c

@@ -8,7 +8,6 @@
 #include "udev.h"
 #include "uarch.h"
 #include "../common/global.h"
-#include "../common/pci.h"
 
 #if defined(__APPLE__) || defined(__MACH__)
   #include "sysctl.h"
@@ -835,43 +834,6 @@ struct system_on_chip* guess_soc_from_uarch(struct system_on_chip* soc, struct c
   return soc;
 }
 
-struct system_on_chip* guess_soc_from_pci(struct system_on_chip* soc, struct cpuInfo* cpu) {
-  struct pci_devices * pci = get_pci_devices();
-  if (pci == NULL) {
-    printWarn("guess_soc_from_pci: Unable to find suitable PCI devices");
-    return soc;
-  }
-
-  typedef struct {
-    uint16_t vendor_id;
-    uint16_t device_id;
-    struct system_on_chip soc;
-  } pciToSoC;
-
-  pciToSoC socFromPCI[] = {
-    {PCI_VENDOR_NVIDIA, PCI_DEVICE_TEGRA_X1, {SOC_TEGRA_X1, SOC_VENDOR_NVIDIA,  20, "Tegra X1", NULL} },
-    // {PCI_VENDOR_NVIDIA, PCI_DEVICE_GH_200,{SOC_GH_200,   SOC_VENDOR_NVIDIA,  ?, "Grace Hopper", NULL} },
-    {0x0000,            0x0000,              {UNKNOWN,      SOC_VENDOR_UNKNOWN, -1,          "", NULL} }
-  };
-
-  int index = 0;
-  while (socFromPCI[index].vendor_id != 0x0) {
-    for (int i=0; i < pci->num_devices; i++) {
-      struct pci_device * dev = pci->devices[i];
-
-      if (socFromPCI[index].vendor_id == dev->vendor_id &&
-          socFromPCI[index].device_id == dev->device_id) {
-        fill_soc(soc, socFromPCI[index].soc.soc_name, socFromPCI[index].soc.soc_model, socFromPCI[index].soc.process);
-        return soc;
-      }
-    }
-    index++;
-  }
-
-  printWarn("guess_soc_from_pci: No PCI device matched the list");
-  return soc;
-}
-
 int hex2int(char c) {
   if (c >= '0' && c <= '9')
     return c - '0';
@@ -1042,18 +1004,14 @@ struct system_on_chip* get_soc(struct cpuInfo* cpu) {
       printWarn("SoC detection failed using Android: Found '%s' string", soc->raw_name);
     }
 #endif // ifdef __ANDROID__
-    // If previous steps failed, try with nvmem
+    // If cpufinfo/Android (if available) detection fails, try with nvmem
     if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
       soc = guess_soc_from_nvmem(soc);
     }
-    // If previous steps failed, try infering it from the microarchitecture
+    // If everything else failed, try infering it from the microarchitecture
     if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
       soc = guess_soc_from_uarch(soc, cpu);
     }
-    // If previous steps failed, try infering it from the pci device id
-    if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
-      soc = guess_soc_from_pci(soc, cpu);
-    }
   }
 #elif defined __APPLE__ || __MACH__
   soc = guess_soc_apple(soc);

src/arm/socs.h

@@ -363,8 +363,6 @@ enum {
   SOC_GOOGLE_TENSOR,
   SOC_GOOGLE_TENSOR_G2,
   SOC_GOOGLE_TENSOR_G3,
-  // NVIDIA,
-  SOC_TEGRA_X1,
   // UNKNOWN
   SOC_MODEL_UNKNOWN
 };
@@ -380,7 +378,6 @@ inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
   else if(soc >= SOC_ALLWINNER_A10 && soc <= SOC_ALLWINNER_R328) return SOC_VENDOR_ALLWINNER;
   else if(soc >= SOC_ROCKCHIP_3288 && soc <= SOC_ROCKCHIP_3588) return SOC_VENDOR_ROCKCHIP;
   else if(soc >= SOC_GOOGLE_TENSOR && soc <= SOC_GOOGLE_TENSOR_G3) return SOC_VENDOR_GOOGLE;
-  else if(soc >= SOC_TEGRA_X1 && soc <= SOC_TEGRA_X1) return SOC_VENDOR_NVIDIA;
   return SOC_VENDOR_UNKNOWN;
 }
 

src/arm/uarch.c

@@ -324,8 +324,6 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
       return 3;
     case UARCH_ICESTORM:    // [https://dougallj.github.io/applecpu/icestorm-simd.html]
     case UARCH_BLIZZARD:    // [https://en.wikipedia.org/wiki/Comparison_of_ARM_processors]
-    case UARCH_TAISHAN_V110:// [https://www-file.huawei.com/-/media/corp2020/pdf/publications/huawei-research/2022/huawei-research-issue1-en.pdf]: "128-bit x 2 for single precision"
-    case UARCH_TAISHAN_V200:// Not confirmed, asssuming same as v110
     case UARCH_CORTEX_A57:  // [https://www.anandtech.com/show/8718/the-samsung-galaxy-note-4-exynos-review/5]
     case UARCH_CORTEX_A72:  // [https://www.anandtech.com/show/10347/arm-cortex-a73-artemis-unveiled/2]
     case UARCH_CORTEX_A73:  // [https://www.anandtech.com/show/10347/arm-cortex-a73-artemis-unveiled/2]

src/common/ascii.h

@@ -360,27 +360,6 @@ $C1##########@@@@@@@@@@@@@@@@############## \
 $C1######################################## \
 $C1  ####################################   "
 
-#define ASCII_NVIDIA \
-"$C1               'cccccccccccccccccccccccccc   \
-$C1               ;oooooooooooooooooooooooool   \
-$C1           .:::.     .oooooooooooooooooool   \
-$C1      .:cll;   ,c:::.     cooooooooooooool   \
-$C1   ,clo'      ;.   oolc:     ooooooooooool   \
-$C1.cloo    ;cclo .      .olc.    coooooooool   \
-$C1oooo   :lo,    ;ll;    looc    :oooooooool   \
-$C1 oooc   ool.   ;oooc;clol    :looooooooool   \
-$C1  :ooc   ,ol;  ;oooooo.   .cloo;     loool   \
-$C1    ool;   .olc.       ,:lool        .lool   \
-$C1      ool:.    ,::::ccloo.        :clooool   \
-$C1         oolc::.            ':cclooooooool   \
-$C1               ;oooooooooooooooooooooooool   \
-$C1                                             \
-$C1                                             \
-$C2######.  ##   ##  ##  ######   ##    ###     \
-$C2##   ##  ##   ##  ##  ##   ##  ##   #: :#    \
-$C2##   ##   ## ##   ##  ##   ##  ##  #######   \
-$C2##   ##    ###    ##  ######   ## ##     ##  "
-
 // --------------------- LONG LOGOS ------------------------- //
 #define ASCII_AMD_L \
 "$C1                                                              \
@@ -513,23 +492,6 @@ $C1        ###########. ############                 \
 $C1            ################                      \
 $C1                 #######                          "
 
-#define ASCII_NVIDIA_L \
-"$C1                  MMMMMMMMMMMMMMMMMMMMMMMMMMMMMM  \
-$C1                  MMMMMMMMMMMMMMMMMMMMMMMMMMMMMM  \
-$C1                .::   'MMMMMMMMMMMMMMMMMMMMMMMMM  \
-$C1           ccllooo;:;.       ;MMMMMMMMMMMMMMMMMM  \
-$C1       cloc       :ooollcc:     :MMMMMMMMMMMMMMM  \
-$C1    cloc      :ccl;      lolc,     ;MMMMMMMMMMMM  \
-$C1.cloo:    :clo    ;c:      .ool;     MMMMMMMMMMM  \
-$C1  ooo:    ooo     :ool,  .cloo.    ;lMMMMMMMMMMM  \
-$C1   ooo:    ooc    :ooooccooo.    :MMMM  lMMMMMMM  \
-$C1     ooc.   ool:  :oooooo'    ,cloo.        MMMM  \
-$C1      ool:.    olc:       .:cloo.          :MMMM  \
-$C1         olc,     ;:::cccloo.          :MMMMMMMM  \
-$C1            olcc::;              ,:ccloMMMMMMMMM  \
-$C1                  :......oMMMMMMMMMMMMMMMMMMMMMM  \
-$C1                  :lllMMMMMMMMMMMMMMMMMMMMMMMMMM  "
-
 typedef struct ascii_logo asciiL;
 
 //                        +-----------------------------------------------------------------------------------------------------------------+
@@ -554,7 +516,6 @@ asciiL logo_riscv       = { ASCII_RISCV,       63, 18, false, {C_FG_CYAN, C_FG_Y
 asciiL logo_sifive      = { ASCII_SIFIVE,      48, 19, true,  {C_BG_WHITE, C_BG_BLACK},                       {C_FG_WHITE,   C_FG_BLUE}    };
 asciiL logo_starfive    = { ASCII_STARFIVE,    33, 17, false, {C_FG_WHITE},                                   {C_FG_WHITE,   C_FG_BLUE}    };
 asciiL logo_sipeed      = { ASCII_SIPEED,      41, 16, true,  {C_BG_RED, C_BG_WHITE},                         {C_FG_RED,     C_FG_WHITE}   };
-asciiL logo_nvidia      = { ASCII_NVIDIA,      45, 19, false, {C_FG_GREEN, C_FG_WHITE},                       {C_FG_WHITE,   C_FG_GREEN}   };
 
 // Long variants          | ----------------------------------------------------------------------------------------------------------------|
 asciiL logo_amd_l       = { ASCII_AMD_L,       62, 19, true,  {C_BG_WHITE, C_BG_GREEN},                       {C_FG_WHITE, C_FG_GREEN}     };
@@ -564,7 +525,6 @@ asciiL logo_arm_l       = { ASCII_ARM_L,       60,  8, true,  {C_BG_CYAN},
 asciiL logo_ibm_l       = { ASCII_IBM_L,       62, 13, true,  {C_BG_CYAN, C_FG_WHITE},                        {C_FG_CYAN,  C_FG_WHITE}     };
 asciiL logo_starfive_l  = { ASCII_STARFIVE_L,  50, 22, false, {C_FG_WHITE},                                   {C_FG_WHITE, C_FG_BLUE}      };
 asciiL logo_sifive_l    = { ASCII_SIFIVE_L,    53, 21, true,  {C_BG_WHITE, C_BG_BLACK},                       {C_FG_WHITE, C_FG_CYAN}      };
-asciiL logo_nvidia_l    = { ASCII_NVIDIA_L,    50, 15, false, {C_FG_GREEN, C_FG_WHITE},                       {C_FG_WHITE, C_FG_GREEN}     };
 asciiL logo_unknown     = { NULL,               0,  0, false, {COLOR_NONE},                                   {COLOR_NONE, COLOR_NONE}     };
 
 #endif

src/common/cpu.h

@@ -32,7 +32,6 @@ enum {
 enum {
   HV_VENDOR_KVM,
   HV_VENDOR_QEMU,
-  HV_VENDOR_VBOX,
   HV_VENDOR_HYPERV,
   HV_VENDOR_VMWARE,
   HV_VENDOR_XEN,

src/common/freq.c

@@ -0,0 +1,154 @@
+#ifdef __linux__
+
+#define _GNU_SOURCE
+
+#include <time.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <sys/ioctl.h>
+#include <linux/perf_event.h>
+
+#include "global.h"
+
+static long
+perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
+                int cpu, int group_fd, unsigned long flags) {
+    int ret;
+    ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
+                    group_fd, flags);
+    return ret;
+}
+
+#define INSERT_ASM_ONCE __asm volatile("nop");
+#define INSERT_ASM_10_TIMES \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+
+#define INSERT_ASM_100_TIMES \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES
+
+#define INSERT_ASM_1000_TIMES \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+
+void nop_function(uint64_t iters) {
+  for (uint64_t i = 0; i < iters; i++) {
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+  }
+}
+
+// Differences between x86 measure_frequency this measure_max_frequency:
+// - measure_frequency employs all cores simultaneously wherease 
+//   measure_max_frequency only employs 1.
+// - measure_frequency runs the computation and checks /proc/cpuinfo whereas
+//   measure_max_frequency does not rely on /proc/cpuinfo and simply
+//   counts cpu cycles to measure frequency.
+// - measure_frequency uses actual computation while measuring the frequency
+//   whereas measure_max_frequency uses nop instructions. This makes the former
+//   x86 dependant whereas the latter is architecture independant.
+int64_t measure_max_frequency(uint32_t core) {
+  if (!bind_to_cpu(core)) {
+    printErr("Failed binding the process to CPU %d", core);
+    return -1;
+  }
+
+  clockid_t clock = CLOCK_PROCESS_CPUTIME_ID;
+
+  struct perf_event_attr pe;
+  uint64_t instructions;
+  int fd;
+  int pid = 0;
+
+  memset(&pe, 0, sizeof(struct perf_event_attr));
+  pe.type = PERF_TYPE_HARDWARE;
+  pe.size = sizeof(struct perf_event_attr);
+  pe.config = PERF_COUNT_HW_CPU_CYCLES;
+  pe.disabled = 1;
+  pe.exclude_kernel = 1;
+  pe.exclude_hv = 1;
+
+  fd = perf_event_open(&pe, pid, core, -1, 0);
+  if (fd == -1) {
+    perror("perf_event_open");
+    if (errno == EPERM || errno == EACCES) {
+      printf("You may not have permission to collect stats.\n");
+      printf("Consider tweaking /proc/sys/kernel/perf_event_paranoid or running as root.\n");
+    }
+    return -1;
+  }
+
+  const char* frequency_banner = "cpufetch is measuring the max frequency...";
+  printf("%s", frequency_banner);
+  fflush(stdout);
+
+  uint64_t iters = 10000000;
+  struct timespec start, end;
+  if (clock_gettime(clock, &start) == -1) {
+    perror("clock_gettime");
+    return -1;
+  }
+  if(ioctl(fd, PERF_EVENT_IOC_RESET, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+  if(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+
+  nop_function(iters);
+
+  read(fd, &instructions, sizeof(uint64_t));
+  if(ioctl(fd, PERF_EVENT_IOC_DISABLE, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+  if (clock_gettime(clock, &end) == -1) {
+    perror("clock_gettime");
+    return -1;
+  }
+
+  uint64_t nsecs = (end.tv_sec*1e9 + end.tv_nsec) - (start.tv_sec*1e9 + start.tv_nsec);
+  uint64_t usecs = nsecs/1000;  
+  double frequency = instructions/((double)usecs);
+
+  printf("\r%*c\r", (int) strlen(frequency_banner), ' ');
+  
+  // Discard last digit in the frequency, which should help providing
+  // more reliable and predictable values.
+  return (((int) frequency + 5)/10) * 10;
+}
+
+#endif // #ifdef __linux__

src/common/freq.h

@@ -0,0 +1,6 @@
+#ifndef __COMMON_FREQ__
+#define __COMMON_FREQ__
+
+int64_t measure_max_frequency(uint32_t core);
+
+#endif

src/common/global.c

@@ -1,3 +1,14 @@
+#ifdef _WIN32
+  #define NOMINMAX
+  #include <windows.h>
+#elif defined __linux__
+  #define _GNU_SOURCE
+  #include <sched.h>
+#elif defined __FreeBSD__
+  #include <sys/param.h>
+  #include <sys/cpuset.h>
+#endif
+
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -199,6 +210,34 @@ void* erealloc(void *ptr, size_t size) {
   return newptr;
 }
 
+#ifndef __APPLE__
+bool bind_to_cpu(int cpu_id) {
+  #ifdef _WIN32
+    HANDLE process = GetCurrentProcess();
+    DWORD_PTR processAffinityMask = 1 << cpu_id;
+    return SetProcessAffinityMask(process, processAffinityMask);
+  #elif defined __linux__
+    cpu_set_t currentCPU;
+    CPU_ZERO(&currentCPU);
+    CPU_SET(cpu_id, &currentCPU);
+    if (sched_setaffinity (0, sizeof(currentCPU), &currentCPU) == -1) {
+      printWarn("sched_setaffinity: %s", strerror(errno));
+      return false;
+    }
+    return true;
+  #elif defined __FreeBSD__
+    cpuset_t currentCPU;
+    CPU_ZERO(&currentCPU);
+    CPU_SET(cpu_id, &currentCPU);
+    if(cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_TID, -1, sizeof(cpuset_t), &currentCPU) == -1) {
+      printWarn("cpuset_setaffinity: %s", strerror(errno));
+      return false;
+    }
+    return true;
+  #endif
+}
+#endif
+
 void print_version(FILE *restrict stream) {
 #ifdef GIT_FULL_VERSION
   fprintf(stream, "cpufetch %s (%s %s)\n", GIT_FULL_VERSION, OS_STR, ARCH_STR);

src/common/global.h

@@ -19,6 +19,9 @@ char *strremove(char *str, const char *sub);
 void* emalloc(size_t size);
 void* ecalloc(size_t nmemb, size_t size);
 void* erealloc(void *ptr, size_t size);
+#ifndef __APPLE__
+bool bind_to_cpu(int cpu_id);
+#endif
 void print_version(FILE *restrict stream);
 
 #endif

src/common/pci.c

@@ -1,178 +0,0 @@
-#define _GNU_SOURCE
-
-#include <sys/stat.h>
-#include <dirent.h>
-
-#include "udev.h"
-#include "global.h"
-#include "pci.h"
-
-#ifndef PATH_MAX
-  #define PATH_MAX 1024
-#endif
-
-#define PCI_PATH "/sys/bus/pci/devices/"
-#define MAX_LENGTH_PCI_DIR_NAME 1024
-
-/*
- * doc: https://wiki.osdev.org/PCI#Class_Codes
- *      https://pci-ids.ucw.cz/read/PC
- */
-#define PCI_VENDOR_ID_AMD    0x1002
-#define CLASS_VGA_CONTROLLER 0x0300
-#define CLASS_3D_CONTROLLER  0x0302
-
-// Return a list of PCI devices containing only
-// the sysfs path
-struct pci_devices * get_pci_paths(void) {
-  DIR *dirp;
-
-  if ((dirp = opendir(PCI_PATH)) == NULL) {
-    perror("opendir");
-    return NULL;
-  }
-
-  struct dirent *dp;
-  int numDirs = 0;  
-  errno = 0;
-
-  while ((dp = readdir(dirp)) != NULL) {
-    if (strcmp(dp->d_name, ".") != 0 && strcmp(dp->d_name, "..") != 0)
-      numDirs++;
-  }  
-  if (errno != 0) {
-    perror("readdir");
-    return NULL;
-  }
-
-  rewinddir(dirp);
-
-  struct pci_devices * pci = emalloc(sizeof(struct pci_devices));
-  pci->num_devices = numDirs;
-  pci->devices = emalloc(sizeof(struct pci_device) * pci->num_devices);
-  char * full_path = emalloc(PATH_MAX * sizeof(char));
-  struct stat stbuf;
-  int i = 0;
-
-  while ((dp = readdir(dirp)) != NULL) {
-    if (strcmp(dp->d_name, ".") == 0 || strcmp(dp->d_name, "..") == 0)
-      continue;
-
-    if (strlen(dp->d_name) > MAX_LENGTH_PCI_DIR_NAME) {
-      printErr("Directory name is too long: %s", dp->d_name);
-      return NULL;
-    }
-
-    memset(full_path, 0, PATH_MAX * sizeof(char));
-    snprintf(full_path, min(strlen(PCI_PATH) + strlen(dp->d_name) + 1, PATH_MAX), "%s%s", PCI_PATH, dp->d_name);    
-
-    if (stat(full_path, &stbuf) == -1) {
-      perror("stat");
-      return NULL;
-    }
-
-    if ((stbuf.st_mode & S_IFMT) == S_IFDIR) {
-      int strLen = min(MAX_LENGTH_PCI_DIR_NAME, strlen(dp->d_name)) + 1;
-      pci->devices[i] = emalloc(sizeof(struct pci_device));
-      pci->devices[i]->path = ecalloc(sizeof(char), strLen);
-      strncpy(pci->devices[i]->path, dp->d_name, strLen);
-      i++;
-    }        
-  }
-  if (errno != 0) {
-    perror("readdir");
-    return NULL;
-  }
-
-  return pci;
-}
-
-// For each PCI device in the list pci, fetch its vendor and 
-// device id using sysfs (e.g., /sys/bus/pci/devices/XXX/{vendor/device})
-void populate_pci_devices(struct pci_devices * pci) {
-  int filelen;
-  char* buf;
-
-  for (int i=0; i < pci->num_devices; i++) {
-    struct pci_device* dev = pci->devices[i];
-    int path_size = strlen(PCI_PATH) + strlen(dev->path) + 2;
-
-    // Read vendor_id
-    char *vendor_id_path = emalloc(sizeof(char) * (path_size + strlen("vendor")));
-    sprintf(vendor_id_path, "%s/%s/%s", PCI_PATH, dev->path, "vendor");
-    
-    if ((buf = read_file(vendor_id_path, &filelen)) == NULL) {
-      printWarn("read_file: %s: %s\n", vendor_id_path, strerror(errno));
-      dev->vendor_id = 0;
-    }
-    else {
-      dev->vendor_id = strtol(buf, NULL, 16);
-    }
-
-    // Read device_id
-    char *device_id_path = emalloc(sizeof(char) * (path_size + strlen("device")));
-    sprintf(device_id_path, "%s/%s/%s", PCI_PATH, dev->path, "device");
-
-    if ((buf = read_file(device_id_path, &filelen)) == NULL) {
-      printWarn("read_file: %s: %s\n", device_id_path, strerror(errno));
-      dev->device_id = 0;
-    }
-    else {
-      dev->device_id = strtol(buf, NULL, 16);
-    }
-
-    free(vendor_id_path);
-    free(device_id_path);
-  }
-}
-
-// Right now, we are interested in PCI devices which
-// vendor is NVIDIA (to be extended in the future).
-// Should we also restrict to VGA controllers only?
-bool pci_device_is_useful(struct pci_device* dev) {
-  return dev->vendor_id == PCI_VENDOR_NVIDIA;
-}
-
-// Filter the input list in order to get only those PCI devices which 
-// we are interested in (decided by pci_device_is_useful)
-// and return the filtered result.
-struct pci_devices * filter_pci_devices(struct pci_devices * pci) {
-  int * devices_to_get = emalloc(sizeof(int) * pci->num_devices);
-  int dev_ptr = 0;
-
-  for (int i=0; i < pci->num_devices; i++) {
-    if (pci_device_is_useful(pci->devices[i])) {
-      devices_to_get[dev_ptr] = i;
-      dev_ptr++;
-    }
-  }
-
-  struct pci_devices * pci_filtered = emalloc(sizeof(struct pci_devices));
-  pci_filtered->num_devices = dev_ptr;
-
-  if (pci_filtered->num_devices == 0) {
-    pci_filtered->devices = NULL;
-  }
-  else {
-    pci_filtered->devices = emalloc(sizeof(struct pci_device) * pci_filtered->num_devices);  
-
-    for (int i=0; i < pci_filtered->num_devices; i++)
-      pci_filtered->devices[i] = pci->devices[devices_to_get[i]];
-  }
-
-  return pci_filtered;
-}
-
-// Return a list of PCI devices that could be used to infer the SoC.
-// The criteria to determine which devices are suitable for this task
-// is decided in filter_pci_devices.
-struct pci_devices * get_pci_devices(void) {
-  struct pci_devices * pci = get_pci_paths();
-
-  if (pci == NULL)
-    return NULL;
-
-  populate_pci_devices(pci);  
-
-  return filter_pci_devices(pci);
-}

src/common/pci.h

@@ -1,20 +0,0 @@
-#ifndef __PCI__
-#define __PCI__
-
-#define PCI_VENDOR_NVIDIA 0x10de
-#define PCI_DEVICE_TEGRA_X1 0x0faf
-
-struct pci_device {
-  char * path;
-  uint16_t vendor_id;
-  uint16_t device_id;
-};
-
-struct pci_devices {
-  struct pci_device ** devices;
-  int num_devices;
-};
-
-struct pci_devices * get_pci_devices(void);
-
-#endif

src/common/printer.c

@@ -61,6 +61,7 @@ enum {
   ATTRIBUTE_NCORES,
   ATTRIBUTE_NCORES_DUAL,
 #ifdef ARCH_X86
+  ATTRIBUTE_SSE,
   ATTRIBUTE_AVX,
   ATTRIBUTE_FMA,
 #elif ARCH_PPC
@@ -96,6 +97,7 @@ static const char* ATTRIBUTE_FIELDS [] = {
   "Cores:",
   "Cores (Total):",
 #ifdef ARCH_X86
+  "SSE:",
   "AVX:",
   "FMA:",
 #elif ARCH_PPC
@@ -131,6 +133,7 @@ static const char* ATTRIBUTE_FIELDS_SHORT [] = {
   "Cores:",
   "Cores (Total):",
 #ifdef ARCH_X86
+  "SSE:",
   "AVX:",
   "FMA:",
 #elif ARCH_PPC
@@ -383,8 +386,6 @@ void choose_ascii_art(struct ascii* art, struct color** cs, struct terminal* ter
     art->art = &logo_allwinner;
   else if(art->vendor == SOC_VENDOR_ROCKCHIP)
     art->art = &logo_rockchip;
-  else if(art->vendor == SOC_VENDOR_NVIDIA)
-    art->art = choose_ascii_art_aux(&logo_nvidia_l, &logo_nvidia, term, lf);
   else {
     art->art = choose_ascii_art_aux(&logo_arm_l, &logo_arm, term, lf);
   }
@@ -591,6 +592,7 @@ bool print_cpufetch_x86(struct cpuInfo* cpu, STYLE s, struct color** cs, struct
   for(int i = 0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
     char* max_frequency = get_str_freq(ptr->freq);
     char* avx = get_str_avx(ptr);
+    char* sse = get_str_sse(ptr);
     char* fma = get_str_fma(ptr);
     char* cpu_num = emalloc(sizeof(char) * 9);
 
@@ -625,8 +627,17 @@ bool print_cpufetch_x86(struct cpuInfo* cpu, STYLE s, struct color** cs, struct
         setAttribute(art, ATTRIBUTE_NCORES, n_cores);
       }
     }
+
+    // Show the most modern vector instructions.
+    // If AVX is supported show it, otherwise show SSE
+    if (strcmp(avx, "No") == 0) {
+      setAttribute(art, ATTRIBUTE_SSE, sse);
+    }
+    else {
       setAttribute(art, ATTRIBUTE_AVX, avx);
       setAttribute(art, ATTRIBUTE_FMA, fma);
+    }
+
     if(l1i != NULL) setAttribute(art, ATTRIBUTE_L1i, l1i);
     if(l1d != NULL) setAttribute(art, ATTRIBUTE_L1d, l1d);
     if(l2 != NULL) setAttribute(art, ATTRIBUTE_L2, l2);

src/common/soc.c

@@ -20,7 +20,6 @@ static char* soc_trademark_string[] = {
   [SOC_VENDOR_APPLE]      = "Apple ",
   [SOC_VENDOR_ROCKCHIP]   = "Rockchip ",
   [SOC_VENDOR_GOOGLE]     = "Google ",
-  [SOC_VENDOR_NVIDIA]     = "NVIDIA ",
   // RISC-V
   [SOC_VENDOR_SIFIVE]     = "SiFive ",
   [SOC_VENDOR_STARFIVE]   = "StarFive ",

src/common/soc.h

@@ -24,7 +24,6 @@ enum {
   SOC_VENDOR_APPLE,
   SOC_VENDOR_ROCKCHIP,
   SOC_VENDOR_GOOGLE,
-  SOC_VENDOR_NVIDIA,
   // RISC-V
   SOC_VENDOR_SIFIVE,
   SOC_VENDOR_STARFIVE,

src/ppc/ppc.c

@@ -14,7 +14,6 @@
 static char *hv_vendors_name[] = {
   [HV_VENDOR_KVM]       = "KVM",
   [HV_VENDOR_QEMU]      = "QEMU",
-  [HV_VENDOR_VBOX]      = "VirtualBox",
   [HV_VENDOR_HYPERV]    = "Microsoft Hyper-V",
   [HV_VENDOR_VMWARE]    = "VMware",
   [HV_VENDOR_XEN]       = "Xen",

src/x86/apic.c

@@ -72,34 +72,6 @@ uint32_t get_apic_id(bool x2apic_id) {
   }
 }
 
-#ifndef __APPLE__
-bool bind_to_cpu(int cpu_id) {
-  #ifdef _WIN32
-    HANDLE process = GetCurrentProcess();
-    DWORD_PTR processAffinityMask = 1 << cpu_id;
-    return SetProcessAffinityMask(process, processAffinityMask);
-  #elif defined __linux__
-    cpu_set_t currentCPU;
-    CPU_ZERO(&currentCPU);
-    CPU_SET(cpu_id, &currentCPU);
-    if (sched_setaffinity (0, sizeof(currentCPU), &currentCPU) == -1) {
-      printWarn("sched_setaffinity: %s", strerror(errno));
-      return false;
-    }
-    return true;
-  #elif defined __FreeBSD__
-    cpuset_t currentCPU;
-    CPU_ZERO(&currentCPU);
-    CPU_SET(cpu_id, &currentCPU);
-    if(cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_TID, -1, sizeof(cpuset_t), &currentCPU) == -1) {
-      printWarn("cpuset_setaffinity: %s", strerror(errno));
-      return false;
-    }
-    return true;
-  #endif
-}
-#endif
-
 #ifdef __linux__
 int get_total_cores_module(int total_cores, int module) {
   int total_modules = 2;
@@ -397,6 +369,11 @@ bool fill_apic_ids(uint32_t* apic_ids, int first_core, int n, bool x2apic_id) {
 }
 
 bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo) {
+  if (topo->cach == NULL) {
+    printWarn("get_topology_from_apic: cach is NULL");
+    return false;
+  }
+
   uint32_t apic_id;
   uint32_t* apic_ids = emalloc(sizeof(uint32_t) * topo->total_cores_module);
   uint32_t* apic_pkg = emalloc(sizeof(uint32_t) * topo->total_cores_module);

src/x86/apic.h

@@ -17,10 +17,6 @@ struct apic {
 bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo);
 uint32_t is_smt_enabled_amd(struct topology* topo);
 
-#ifndef __APPLE__
-bool bind_to_cpu(int cpu_id);
-#endif
-
 #ifdef __linux__
 int get_total_cores_module(int total_cores, int module);
 #endif

src/x86/cpuid.c

@@ -6,6 +6,10 @@
   #include <unistd.h>
 #endif
 
+#ifdef __linux__
+  #include "../common/freq.h"
+#endif
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -26,7 +30,6 @@
 static const char *hv_vendors_string[] = {
   [HV_VENDOR_KVM]       = "KVMKVMKVM",
   [HV_VENDOR_QEMU]      = "TCGTCGTCGTCG",
-  [HV_VENDOR_VBOX]      = "VBoxVBoxVBox",
   [HV_VENDOR_HYPERV]    = "Microsoft Hv",
   [HV_VENDOR_VMWARE]    = "VMwareVMware",
   [HV_VENDOR_XEN]       = "XenVMMXenVMM",
@@ -39,7 +42,6 @@ static const char *hv_vendors_string[] = {
 static char *hv_vendors_name[] = {
   [HV_VENDOR_KVM]       = "KVM",
   [HV_VENDOR_QEMU]      = "QEMU",
-  [HV_VENDOR_VBOX]      = "VirtualBox",
   [HV_VENDOR_HYPERV]    = "Microsoft Hyper-V",
   [HV_VENDOR_VMWARE]    = "VMware",
   [HV_VENDOR_XEN]       = "Xen",
@@ -218,7 +220,7 @@ int64_t get_peak_performance(struct cpuInfo* cpu, bool accurate_pp) {
   #endif
 
     //First, check we have consistent data
-    if(freq == UNKNOWN_DATA || topo->logical_cores == UNKNOWN_DATA) {
+    if(freq == UNKNOWN_DATA || topo == NULL || topo->logical_cores == UNKNOWN_DATA) {
       return -1;
     }
 
@@ -451,7 +453,7 @@ struct cpuInfo* get_cpu_info(void) {
   cpu->cach = NULL;
   cpu->feat = NULL;
 
-  uint32_t modules = 1;
+  cpu->num_cpus = 1;
   uint32_t eax = 0;
   uint32_t ebx = 0;
   uint32_t ecx = 0;
@@ -507,12 +509,12 @@ struct cpuInfo* get_cpu_info(void) {
     cpu->hybrid_flag = (edx >> 15) & 0x1;
   }
 
-  if(cpu->hybrid_flag) modules = 2;
+  if(cpu->hybrid_flag) cpu->num_cpus = 2;
 
   struct cpuInfo* ptr = cpu;
-  for(uint32_t i=0; i < modules; i++) {
+  for(uint32_t i=0; i < cpu->num_cpus; i++) {
     int32_t first_core;
-    set_cpu_module(i, modules, &first_core);
+    set_cpu_module(i, cpu->num_cpus, &first_core);
 
     if(i > 0) {
       ptr->next_cpu = emalloc(sizeof(struct cpuInfo));
@@ -547,11 +549,7 @@ struct cpuInfo* get_cpu_info(void) {
       cpu->cpu_name = infer_cpu_name_from_uarch(cpu->arch);
     }
 
-    // If any field of the struct is NULL,
-    // return early, as next functions
-    // require non NULL fields in cach and topo
     ptr->cach = get_cache_info(ptr);
-    if(ptr->cach == NULL) return cpu;
 
     if(cpu->hybrid_flag) {
       ptr->topo = get_topology_info(ptr, ptr->cach, i);
@@ -559,16 +557,23 @@ struct cpuInfo* get_cpu_info(void) {
     else {
       ptr->topo = get_topology_info(ptr, ptr->cach, -1);
     }
-    if(cpu->topo == NULL) return cpu;
+
+    // If topo is NULL, return early, as get_peak_performance
+    // requries non-NULL topology.
+    if(ptr->topo == NULL) return cpu;
   }
 
-  cpu->num_cpus = modules;
   cpu->peak_performance = get_peak_performance(cpu, accurate_pp());
 
   return cpu;
 }
 
 bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
+  if (topo->cach == NULL) {
+    printWarn("get_cache_topology_amd: cach is NULL");
+    return false;
+  }
+
   if(cpu->maxExtendedLevels >= 0x8000001D && cpu->topology_extensions) {
     uint32_t i, eax, ebx, ecx, edx, num_sharing_cache, cache_type, cache_level;
 
@@ -644,10 +649,12 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
 
 #ifdef __linux__
 void get_topology_from_udev(struct topology* topo) {
-  // TODO: To be improved in the future
   topo->total_cores = get_ncores_from_cpuinfo();
-  topo->logical_cores = topo->total_cores;
-  topo->physical_cores = topo->total_cores;
+  // TODO: To be improved in the future
+  // Conservative setting as we only know the total
+  // number of cores.
+  topo->logical_cores = UNKNOWN_DATA;
+  topo->physical_cores = UNKNOWN_DATA;
   topo->smt_available = 1;
   topo->smt_supported = 1;
   topo->sockets = 1;
@@ -711,8 +718,8 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, int
       }
       else {
         printWarn("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000001, cpu->maxLevels);
-        topo->physical_cores = 1;
-        topo->logical_cores = 1;
+        topo->physical_cores = UNKNOWN_DATA;
+        topo->logical_cores = UNKNOWN_DATA;
         topo->smt_available = 1;
         topo->smt_supported = 1;
       }
@@ -962,6 +969,14 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
     }
   }
 
+  #ifdef __linux__
+    if (freq->max == UNKNOWN_DATA) {
+      printWarn("All previous methods failed, measuring CPU frequency");
+      // TODO: Support hybrid architectures
+      freq->max = measure_max_frequency(0);
+    }
+  #endif
+
   return freq;
 }
 

src/x86/freq/freq.h

@@ -9,5 +9,6 @@
 #define LOOP_ITERS           100000000
 
 int64_t measure_frequency(struct cpuInfo* cpu);
+void nop_function_x86(uint64_t iters);
 
 #endif

src/x86/uarch.c

@@ -382,7 +382,6 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
   CHECK_UARCH(arch, 10, 15,  5,  0, NA, "Zen 3",       UARCH_ZEN3,         7) // instlatx64
   CHECK_UARCH(arch, 10, 15,  6,  1,  2, "Zen 4",       UARCH_ZEN4,         5) // instlatx64
   CHECK_UARCH(arch, 10, 15,  7,  4,  1, "Zen 4",       UARCH_ZEN4,         4) // instlatx64
-  CHECK_UARCH(arch, 10, 15,  7,  5,  2, "Zen 4",       UARCH_ZEN4,         4) // instlatx64
   CHECK_UARCH(arch, 10, 15,  7,  8,  0, "Zen 4",       UARCH_ZEN4,         4) // instlatx64
   CHECK_UARCH(arch, 10, 15,  8, NA, NA, "Zen 4",       UARCH_ZEN4,         5) // instlatx64 (AMD MI300C)
   CHECK_UARCH(arch, 10, 15,  9, NA, NA, "Zen 4",       UARCH_ZEN4,         5) // instlatx64 (AMD MI300A)